© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10970
    Prev
    Next
    INDEX
    Explanations

    references to studies, apps, code and tables

    oai_token-act-pair · gemini-2.0-flash

    General conversational language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    memberof
    -0.46
    co
    -0.43
     články
    -0.41
    waitUntil
    -0.40
    ЛЯ
    -0.40
     $\
    -0.40
     republiky
    -0.40
    -0.40
    assertThat
    -0.39
    quot
    -0.38
    POSITIVE LOGITS
     myſelf
    0.82
     leaſt
    0.79
    setVerticalGroup
    0.79
     Monfieur
    0.78
    tonode
    0.71
     kaarangay
    0.69
    PerformLayout
    0.68
    .*")]
    0.68
     themſelves
    0.66
     дописавши
    0.66
    Activations Density 4.064%

    No Known Activations